极限学习机模型的土壤含水量反演研究Soil water content inversion based on extreme learning machine model
李向龙,赵洪丽,赵红莉,王镕,郝震
摘要(Abstract)：
针对传统反馈型神经网络模型在土壤含水量反演时容易陷入局部最优解和模型计算效率低等问题,该文提出了极限学习机模型结合主被动遥感进行土壤含水量反演的方法。首先,使用水云模型计算裸土后向散射系数,通过高级积分方程模型建立组合地表粗糙度库,计算各点的地表粗糙度;其次,以计算的裸土后向散射系数、植被指数、地表粗糙度和入射角作为输入数据,以土壤含水量为输出,构建极限学习机模型,并进行训练;最后,对极限学习机土壤含水量反演结果进行验证。结果表明,该方法反演土壤含水量具有较高的精度和计算效率;同时,与BP神经网络模型的反演结果比较,证明了该方法的有效性,为土壤含水量的反演研究提供了一种方法。
关键词(KeyWords)： 极限学习机;BP神经网络模型;水云模型;土壤含水量;Sentinel-1/2
基金项目(Foundation): 国家重点研发专项(2018YF C0407705);; 中国水利水电科学研究院科研专项(WR0145B012017,WR0145B272016);; 兰州交通大学优秀平台项目(201806)
作者(Author): 李向龙,赵洪丽,赵红莉,王镕,郝震
DOI: 10.16251/j.cnki.1009-2307.2021.12.013
参考文献(References)：
- [1] 张清河，徐飞，朱国强.一种裸露土壤湿度反演方法[J].测绘科学，2016,41(2):11-14.(ZHANG Qinghe,XU Fei,ZHU Guoqiang.A method for inversion of bare soil moisture[J].Science of Surveying and Mapping,2016,41(2):11-14.)
- [2] CUI H Z,JIANG L Z,ZHOU Z,et al.Downscaling of QP model with dual-channel soil moisture retrievals over Genhe Area in China[C]//IEEE International Geoscience and Remote Sensing Symposium.Valencia,Spain:IEEE,2018:9118-9121.
- [3] 余凡，赵英时，李海涛.基于遗传BP神经网络的主被动遥感协同反演土壤水分[J].红外与毫米波学报，2012,31(3):283-288.(YU Fan,ZHAO Yingshi,LI Haitao.Active passive remote sensing collaborative retrieval of soil moisture based on genetic BP neural network[J].Journal of Infrared and Millimeter Wave,2012,31(3):283-288.)
- [4] HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/2/3):489-501.
- [5] 王婷婷，冯起，温小虎，等.基于极限学习机的干旱区潜在蒸发量模拟[J].中国沙漠，2017,37(6):1219-1226.(WANG Tingting,FENG Qi,WEN Xiaohu,et al.Simulation of potential evaporation in arid area based on extreme learning machine[J].China Desert,2017,37(6):1219-1226.)
- [6] 王鹤，曾永年.城市扩展极限学习机模型[J].测绘学报，2018,47(12):1680-1690.(WANG He,ZENG Yongnian.Limit learning machine model of urban expansion[J].Acta Geodaetica et Cartographica Sinica,2018,47(12):1680-1690.)
- [7] 牟多铎，刘磊.ELM 与 SVM 在高光谱遥感图像监督分类中的比较研究[J].遥感技术与应用，2019,34(1):115-124.(MOU Duoduo,LIU Lei.A comparative study of ELM and SVM in the supervised classification of hyperspectral remote sensing images[J].Remote Sensing Technology and Application,2019,34(1):115-124.)
- [8] BARZEGAR R,GHASRI M,QI Z M,et al.Using bootstrap ELM and LSSVM models to estimate river ice thickness in the Mackenzie River Basin in the Northwest Territories,Canada[J].Journal of Hydrology,2019,577:123903.
- [9] 刘振男，杜尧，韩幸烨，等.基于遗传算法优化极限学习机模型的干旱预测：以云贵高原为例[J].人民长江，2020,51(8):13-18.(LIU Zhennan,DU Yao,HAN Xingye,et al.Drought prediction based on genetic algorithm-optimized extreme learning machine model:case of Yunnan-Guizhou Plateau[J].Yangtze River,2020,51(8):13-18.)
- [10] 钱瑞秋.甘肃疏勒河流域灌区农业用水动态预测及优化配置研究[J].地下水，2020,42(4):83-85.(QIAN Ruiqiu.Study on the dynamic prediction and optimal allocation of agricultural water use in the irrigation area of the Shule River Basin in Gansu[J].Groundwater,2020,42(4):83-85.)
- [11] 孔金玲，甄珮珮，李菁菁，等.基于新的组合粗糙度参数的土壤水分微波遥感反演[J].地理与地理信息科学，2016,32(3):34-38.(KONG Jinling,ZHEN Peipei,LI Jingjing,et al.Retrieval for soil moisture using microwave remote sensing data based on a new combined roughness parameter[J].Geography and Geo-Information Science,2016,32(3):34-38.)
- [12] 杜培军.RADARSAT图像滤波的研究[J].中国矿业大学学报，2002,31(2):132-137.(DU Peijun.Research on RADARSAT image filtering[J].Journal of China University of Mining and Technology,2002,31(2):132-137.)
- [13] 曾旭婧，邢艳秋，单炜，等.基于Sentinel-1A与Landsat 8数据的北黑高速沿线地表土壤水分遥感反演方法研究[J].中国生态农业学报，2017,25(1):118-126.(ZENG Xujing,XING Yanqiu,SHAN Wei,et al.Soil water content retrieval based on Sentinel-1A and Landsat 8 image for Bei’an-Heihe expressway[J].Chinese Journal of Eco-Agriculture,2017,25(1):118-126.)
- [14] ATTEMA E P W,ULABY F T.Vegetation modeled as a water cloud[J].Radio Science,1978,13(2):357-364.
- [15] BINDISH R,BARROS A P.Parameterization of vegetation backscatter in radar-based,soil moisture estimation[J].Remote Sensing of Environment,2001,76(1):130-137.
- [16] JACKSON T J,VINE D M L,HSU A Y,et al.Soil moisture mapping at regional scales using microwave radiometry:the Southern Great Plains hydrology experiment[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2136-2151.
- [17] FUNG A K,LI Z,CHEN K S.Backscattering from a randomly rough dielectric surface[J].IEEE Transactions on Geoscience and Remote Sensing,1992,30(2):356-369.
- [18] FUNG A K,CHEN K S.An update on the IEM surface backscattering model[J].IEEE Geoscience and Remote Sensing Letters,2004,1(2):75-77.
- [19] 李平湘，刘致曲，杨杰，等.利用随机森林回归进行极化SAR土壤水分反演[J].武汉大学学报(信息科学版),2019,44(3):405-412.(LI Pingxiang,LIU Zhiqu,YANG Jie,et al.Soil moisture retrieval of winter wheat fields based on random forest regression using quad-polarimetric SAR images[J].Geomatics and Information Science of Wuhan University,2019,44(3):405-412.)
- [20] 刘啸然，李茂善，胡文斌.藏北高原那曲地区不同下垫面地表粗糙度的变化特征研究[J].高原气象，2019,38(2):428-438.(LIU Xiaoran,LI Maoshan,HU Wenbin.Variations of surface roughness on different underlying surface at Nagqu Area over the Qinghai-Tibetan Plateau[J].Plateau Meteorology,2019,38(2):428-438.)
- [21] ZRIBI M,DECHAMBRE M.A new empirical model to retrieve soil moisture and roughness from C-band radar data[J].Remote Sensing of Environment,2003,84(1):42-52.